Adaptive Memory-Enhanced Time Delay Reservoir and its Memristive Implementation

Xinming SHI, Leandro L. MINKU*, Xin YAO*

*Corresponding author for this work

Research output: Journal PublicationsJournal Article (refereed)peer-review

7 Citations (Scopus)


Time Delay Reservoir (TDR) is a hardware-friendly machine learning approach from two perspectives. First, it can prevent the connection overhead of neural networks with increasing neurons. Second, through its dynamic system representation, TDR can also be implemented in hardware by different systems. However, it performs poorly on tasks that involve long-term dependency. In this work, we first introduce a higher-order delay unit, which is capable of accumulating and transferring the long history states in an adaptive manner to further enhance the reservoir memory. Particle Swarm Optimisation is applied to optimize the enhanced degree of memory adaptivity. Our experiments demonstrate its superiority both for short-A nd long-term memory datasets over seven existing approaches. In light of the hardware-friendly feature of TDR, we further propose a memristive implementation of our adaptive memory-enhanced TDR, where a dynamic memristor and the memristor-based delay element are applied to construct the reservoir. Through circuit simulation, the feasibility of our proposed memristive implementation is verified. The comparisons with different hardware reservoirs show that our proposed memristive implementation is effective both for short-A nd long-term memory datasets, while exhibiting benefits in terms of smaller circuit area and lower power consumption compared with traditional hardware reservoirs.

Original languageEnglish
Pages (from-to)2766-2777
Number of pages12
JournalIEEE Transactions on Computers
Issue number11
Publication statusPublished - 1 Nov 2022
Externally publishedYes

Bibliographical note

Publisher Copyright:
© 1968-2012 IEEE.


  • memristor
  • Time delay reservoir
  • time series prediction


Dive into the research topics of 'Adaptive Memory-Enhanced Time Delay Reservoir and its Memristive Implementation'. Together they form a unique fingerprint.

Cite this